Training in progress, step 2, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 21822612
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:659241f026a607b492fa07c34068900332bf91782f78b07f3ecec93d03feb253
|
3 |
size 21822612
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ca292942a33fa15be81e314818ff2851b6484a4703be8f6939dc3d3e46daa1ae
|
3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a2972d8cacb091bd0e98bfff54b2e4933301753087ce149a9bf9a205a5e2d795
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
5 |
"eval_steps": 1,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -22,6 +22,21 @@
|
|
22 |
"eval_samples_per_second": 12.72,
|
23 |
"eval_steps_per_second": 12.72,
|
24 |
"step": 1
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
25 |
}
|
26 |
],
|
27 |
"logging_steps": 1,
|
@@ -36,12 +51,12 @@
|
|
36 |
"should_evaluate": false,
|
37 |
"should_log": false,
|
38 |
"should_save": true,
|
39 |
-
"should_training_stop":
|
40 |
},
|
41 |
"attributes": {}
|
42 |
}
|
43 |
},
|
44 |
-
"total_flos":
|
45 |
"train_batch_size": 1,
|
46 |
"trial_name": null,
|
47 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.456141563558443e-05,
|
5 |
"eval_steps": 1,
|
6 |
+
"global_step": 2,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
22 |
"eval_samples_per_second": 12.72,
|
23 |
"eval_steps_per_second": 12.72,
|
24 |
"step": 1
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 3.456141563558443e-05,
|
28 |
+
"grad_norm": NaN,
|
29 |
+
"learning_rate": 4e-05,
|
30 |
+
"loss": 0.0,
|
31 |
+
"step": 2
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"epoch": 3.456141563558443e-05,
|
35 |
+
"eval_loss": NaN,
|
36 |
+
"eval_runtime": 238.5611,
|
37 |
+
"eval_samples_per_second": 12.768,
|
38 |
+
"eval_steps_per_second": 12.768,
|
39 |
+
"step": 2
|
40 |
}
|
41 |
],
|
42 |
"logging_steps": 1,
|
|
|
51 |
"should_evaluate": false,
|
52 |
"should_log": false,
|
53 |
"should_save": true,
|
54 |
+
"should_training_stop": true
|
55 |
},
|
56 |
"attributes": {}
|
57 |
}
|
58 |
},
|
59 |
+
"total_flos": 43752345305088.0,
|
60 |
"train_batch_size": 1,
|
61 |
"trial_name": null,
|
62 |
"trial_params": null
|